88056f97-3ba0-4458-8b7e-20f8bb782cbe

pending completion

Build # 88056f97-3ba0-4458-8b7e-20f8bb782cbe

Build Type

Pull #787

circle-ci

Committed by

xzdandy

Commit Message

Check Notebook under ray

Pull Request Pull Request #787: Enable ray be default

Run Details

9700 of 10045 relevant lines covered (96.57%)

0.97 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

96.83

/eva/executor/executor_utils.py

# coding=utf-8
# Copyright 2018-2022 EVA
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import glob
import os
from pathlib import Path
from typing import Generator, List

import cv2

from eva.catalog.catalog_manager import CatalogManager
from eva.catalog.catalog_type import VectorStoreType
from eva.expression.abstract_expression import AbstractExpression
from eva.models.storage.batch import Batch
from eva.parser.table_ref import TableInfo
from eva.parser.types import FileFormatType
from eva.readers.document.registry import SUPPORTED_TYPES
from eva.utils.logging_manager import logger


class ExecutorError(Exception):
    pass


def apply_project(batch: Batch, project_list: List[AbstractExpression]):
    if not batch.empty() and project_list:
        batches = [expr.evaluate(batch) for expr in project_list]
        batch = Batch.merge_column_wise(batches)
    return batch


def apply_predicate(batch: Batch, predicate: AbstractExpression) -> Batch:
    if not batch.empty() and predicate is not None:
        outcomes = predicate.evaluate(batch)
        batch.drop_zero(outcomes)
    return batch


def handle_if_not_exists(table_info: TableInfo, if_not_exist=False):
    # Table exists
    if CatalogManager().check_table_exists(
        table_info.table_name,
        table_info.database_name,
    ):
        err_msg = "Table: {} already exists".format(table_info)
        if if_not_exist:
            logger.warn(err_msg)
            return True
        else:
            logger.error(err_msg)
            raise ExecutorError(err_msg)
    # Table does not exist
    else:
        return False


def validate_image(image_path: Path) -> bool:
    try:
        data = cv2.imread(str(image_path))
        return data is not None
    except Exception as e:
        logger.warning(
            f"Unexpected Exception {e} occurred while reading image file {image_path}"
        )
        return False


def iter_path_regex(path_regex: Path) -> Generator[str, None, None]:
    return glob.iglob(os.path.expanduser(path_regex), recursive=True)


def validate_video(video_path: Path) -> bool:
    try:
        vid = cv2.VideoCapture(str(video_path))
        if not vid.isOpened():
            return False
        return True
    except Exception as e:
        logger.warning(
            f"Unexpected Exception {e} occurred while reading video file {video_path}"
        )


def validate_document(doc_path: Path) -> bool:
    return doc_path.suffix in SUPPORTED_TYPES


def validate_pdf(doc_path: Path) -> bool:
    return doc_path.suffix == ".pdf"


def validate_media(file_path: Path, media_type: FileFormatType) -> bool:
    if media_type == FileFormatType.VIDEO:
        return validate_video(file_path)
    elif media_type == FileFormatType.IMAGE:
        return validate_image(file_path)
    elif media_type == FileFormatType.DOCUMENT:
        return validate_document(file_path)
    elif media_type == FileFormatType.PDF:
        return validate_pdf(file_path)
    else:
        raise ValueError(f"Unsupported Media type {str(media_type)}")


def handle_vector_store_params(
    vector_store_type: VectorStoreType, index_path: str
) -> dict:
    """Handle vector store parameters based on the vector store type and index path.

    Args:
        vector_store_type (VectorStoreType): The type of vector store.
        index_path (str): The path to store the index.

    Returns:
        dict: Dictionary containing the appropriate vector store parameters.


    Raises:
        ValueError: If the vector store type in the node is not supported.
    """
    if vector_store_type == VectorStoreType.FAISS:
        return {"index_path": index_path}
    elif vector_store_type == VectorStoreType.QDRANT:
        return {"index_db": str(Path(index_path).parent)}
    else:
        raise ValueError("Unsupported vector store type: {}".format(vector_store_type))

1	# coding=utf-8
2	# Copyright 2018-2022 EVA
3	#
4	# Licensed under the Apache License, Version 2.0 (the "License");
5	# you may not use this file except in compliance with the License.
6	# You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	import glob	1✔
16	import os	1✔
17	from pathlib import Path	1✔
18	from typing import Generator, List	1✔
19
20	import cv2	1✔
21
22	from eva.catalog.catalog_manager import CatalogManager	1✔
23	from eva.catalog.catalog_type import VectorStoreType	1✔
24	from eva.expression.abstract_expression import AbstractExpression	1✔
25	from eva.models.storage.batch import Batch	1✔
26	from eva.parser.table_ref import TableInfo	1✔
27	from eva.parser.types import FileFormatType	1✔
28	from eva.readers.document.registry import SUPPORTED_TYPES	1✔
29	from eva.utils.logging_manager import logger	1✔
30
31
32	class ExecutorError(Exception):	1✔
33	pass	1✔
34
35
36	def apply_project(batch: Batch, project_list: List[AbstractExpression]):	1✔
37	if not batch.empty() and project_list:	1✔
38	batches = [expr.evaluate(batch) for expr in project_list]	1✔
39	batch = Batch.merge_column_wise(batches)	1✔
40	return batch	1✔
41
42
43	def apply_predicate(batch: Batch, predicate: AbstractExpression) -> Batch:	1✔
44	if not batch.empty() and predicate is not None:	1✔
45	outcomes = predicate.evaluate(batch)	1✔
46	batch.drop_zero(outcomes)	1✔
47	return batch	1✔
48
49
50	def handle_if_not_exists(table_info: TableInfo, if_not_exist=False):	1✔
51	# Table exists
52	if CatalogManager().check_table_exists(	1✔
53	table_info.table_name,
54	table_info.database_name,
55	):
56	err_msg = "Table: {} already exists".format(table_info)	1✔
57	if if_not_exist:	1✔
58	logger.warn(err_msg)	1✔
59	return True	1✔
60	else:
61	logger.error(err_msg)	1✔
62	raise ExecutorError(err_msg)
63	# Table does not exist
64	else:
65	return False	1✔
66
67
68	def validate_image(image_path: Path) -> bool:	1✔
69	try:	1✔
70	data = cv2.imread(str(image_path))	1✔
71	return data is not None	1✔
72	except Exception as e:
73	logger.warning(
74	f"Unexpected Exception {e} occurred while reading image file {image_path}"
75	)
76	return False
77
78
79	def iter_path_regex(path_regex: Path) -> Generator[str, None, None]:	1✔
80	return glob.iglob(os.path.expanduser(path_regex), recursive=True)	1✔
81
82
83	def validate_video(video_path: Path) -> bool:	1✔
84	try:	1✔
85	vid = cv2.VideoCapture(str(video_path))	1✔
86	if not vid.isOpened():	1✔
87	return False	1✔
88	return True	1✔
89	except Exception as e:
90	logger.warning(
91	f"Unexpected Exception {e} occurred while reading video file {video_path}"
92	)
93
94
95	def validate_document(doc_path: Path) -> bool:	1✔
96	return doc_path.suffix in SUPPORTED_TYPES	1✔
97
98
99	def validate_pdf(doc_path: Path) -> bool:	1✔
100	return doc_path.suffix == ".pdf"	1✔
101
102
103	def validate_media(file_path: Path, media_type: FileFormatType) -> bool:	1✔
104	if media_type == FileFormatType.VIDEO:	1✔
105	return validate_video(file_path)	1✔
106	elif media_type == FileFormatType.IMAGE:	1✔
107	return validate_image(file_path)	1✔
108	elif media_type == FileFormatType.DOCUMENT:	1✔
109	return validate_document(file_path)	1✔
110	elif media_type == FileFormatType.PDF:	1✔
111	return validate_pdf(file_path)	1✔
112	else:
113	raise ValueError(f"Unsupported Media type {str(media_type)}")
114
115
116	def handle_vector_store_params(	1✔
117	vector_store_type: VectorStoreType, index_path: str
118	) -> dict:
119	"""Handle vector store parameters based on the vector store type and index path.
120
121	Args:
122	vector_store_type (VectorStoreType): The type of vector store.
123	index_path (str): The path to store the index.
124
125	Returns:
126	dict: Dictionary containing the appropriate vector store parameters.
127
128
129	Raises:
130	ValueError: If the vector store type in the node is not supported.
131	"""
132	if vector_store_type == VectorStoreType.FAISS:	1✔
133	return {"index_path": index_path}	1✔
134	elif vector_store_type == VectorStoreType.QDRANT:	×
135	return {"index_db": str(Path(index_path).parent)}	×
136	else:
137	raise ValueError("Unsupported vector store type: {}".format(vector_store_type))

georgia-tech-db / eva / 88056f97-3ba0-4458-8b7e-20f8bb782cbe

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous